Explore the directory

An Avatar-themed set of configuration files that turns the Cursor editor into a multi-agent development team, with eight specialist agents, per-agent model routing, and git hooks that block risky commits.

• Agent skills
• Editors

A minimal FastAPI backend that demonstrates retrieval-augmented generation with vector similarity search, built for learning and for wiring into a frontend.

• RAG
• Tutorials

A self-hosted AI workspace that chats with more than 300 models across nine providers using your own API keys, with injectable agent skills and self-drafting agents, and no ENZO account or subscription.

• Inference
• LLM gateways

A curated list of AI agent projects built with Anthropic, Gemini, OpenAI and open-source models.

• Curated lists

A native Rust inference server for running open models on NVIDIA GPUs and Apple Silicon, with OpenAI- and Anthropic-compatible APIs and a bundled Studio for comparing models.

• Inference

A router that sits between an app and a pool of AI providers such as Gemini, OpenRouter and Groq, trying the next provider automatically when one is rate-limited, behind one OpenAI- and Anthropic-compatible endpoint.

• LLM gateways

An example internal AI chatbot, built for a fictional investment research firm, that lets analysts query a corpus of financial filings in plain English and get sourced answers.

• RAG
• Tutorials

An enterprise Java AI agent server, built on Spring Boot and LangChain4j, combining ReAct reasoning, hybrid retrieval-augmented generation, and semantic caching for knowledge Q&A.

• Agent frameworks
• RAG

A from-scratch decoder-only language model implementation in pure Rust, covering tokenization, training, quantization, alignment, multimodal input, and an inference server.

• Models

A curated list of competitions, simulators, frameworks, datasets and papers for building autonomous drone racing software, covering events such as the Anduril AI Grand Prix and A2RL.

• Curated lists

A vLLM plugin, built on the FlagOS multi-chip backend, that lets the same vLLM commands run model inference across many different AI chip vendors without changing vLLM's interfaces.

• Inference

A small, dependency-free neural-network framework written in pure Go, with hand-written AVX2 and NEON SIMD kernels for training and inference on ordinary CPUs.

• Models
• Libraries

The official research codebase for a training method that stabilizes distilling a large teacher agent's behavior into a smaller student agent across long, multi-turn tasks.

• Models
• Papers

An MCP server that lets Claude Code hand off bounded coding tasks to a local or cheaper cloud model, cutting token spend while Claude reviews the returned work.

• MCP servers

An introductory Chinese-language course on data and AI fundamentals, teaching how to build AI agents from a data-driven perspective through two parallel learning tracks.

• Tutorials

A Spring Boot starter that turns existing REST controllers into MCP tools automatically, without adding annotations or duplicating business logic into a parallel code path.

• MCP servers

A command-line security scanner that discovers exposed MCP servers, A2A agent cards, and open LLM inference APIs across a network in a single scan.

• Security

A GitHub Skills hands-on exercise that teaches agent orchestration by using custom agents in GitHub Copilot CLI to plan, design, build, and validate a small dashboard.

• Tutorials

The ROS 2 package set that parses .msg, .srv and .action interface definition files and generates the C and C++ code robots use to construct and pass those messages.

• Libraries

A one-click Windows installer that sets up a local Z-Image Turbo image-generation model behind a Gradio web interface, tuned for GPUs with as little as 4 GB of VRAM.

• Generative media

An MCP tool set for Unity that lets an AI agent create and edit animation clips and animator controllers from natural-language commands inside the Unity editor.

• MCP servers

A Windows-first reliability plugin for the OpenCode desktop agent that adds edit boundaries, command evidence, and verification gates around its AI-generated diffs.

• Coding agents
• AI evals

An MCP server that gives multiple coding-agent clients on one machine shared vector memory, an orchestration protocol, and an agent registry so they do not duplicate work.

• MCP servers
• Agent memory

A bilingual, mental-model-first reference on audio machine learning, covering datasets, transformer architectures, speech recognition, text-to-speech, and production voice pipelines.

• Speech
• Books